SOTAVerified

Model Compression

Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 301–350 of 1356 papers

TitleStatusHype
Runtime Tunable Tsetlin Machines for Edge Inference on eFPGAs—0
Systematic Outliers in Large Language ModelsCode0
Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models—0
Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks—0
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity—0
MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks—0
Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data—0
Attention Sinks and Outlier Features: A 'Catch, Tag, and Release' Mechanism for Embeddings—0
Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference—0
Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models—0
Efficient Supernet Training with Orthogonal Softmax for Scalable ASR Model Compression—0
Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural NetworksCode0
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models—0
On Accelerating Edge AI: Optimizing Resource-Constrained Environments—0
You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning—0
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models—0
Practical quantum federated learning and its experimental demonstration—0
MultiPruner: Balanced Structure Removal in Foundation Models—0
FASP: Fast and Accurate Structured Pruning of Large Language Models—0
Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images—0
Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures—0
SWSC: Shared Weight for Similar Channel in LLM—0
Tensorization of neural networks for improved privacy and interpretabilityCode0
Neural Architecture Codesign for Fast Physics ApplicationsCode0
UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehicles—0
CURing Large Models: Compression via CUR Decomposition—0
Effective and Efficient Mixed Precision Quantization of Speech Foundation Models—0
Strategic Fusion Optimizes Transformer Compression—0
Optimizing Small Language Models for In-Vehicle Function-Calling—0
DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the EdgeCode0
Once-Tuning-Multiple-Variants: Tuning Once and Expanded as Multiple Vision-Language Model Variants—0
Random Conditioning for Diffusion Model Compression with Distillation—0
Improving Acoustic Scene Classification in Low-Resource Conditions—0
Feature Alignment-Based Knowledge Distillation for Efficient Compression of Large Language Models—0
Optimization and Scalability of Collaborative Filtering Algorithms in Large Language Models—0
HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge DistillationCode0
Edge-AI for Agriculture: Lightweight Vision Models for Disease Detection in Resource-Limited Settings—0
GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference—0
CoSurfGS:Collaborative 3D Surface Gaussian Splatting with Distributed Learning for Large Scene Reconstruction—0
Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights RefinementCode0
Lightweight Design and Optimization methods for DCNNs: Progress and Futures—0
Semantics Prompting Data-Free Quantization for Low-Bit Vision Transformers—0
Deploying Foundation Model Powered Agent Services: A Survey—0
RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image ClassificationCode0
TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs—0
Can Students Beyond The Teacher? Distilling Knowledge from Teacher's Bias—0
Activation Sparsity Opportunities for Compressing General Large Language Models—0
Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge Devices—0
Low-Rank Correction for Quantized LLMs—0
Lossless Model Compression via Joint Low-Rank Factorization Optimization—0
Show:102550
← PrevPage 7 of 28Next →
All datasetsImageNetQNLI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ADLIK-MO-ResNet50+W4A4Top-177.88—Unverified
2ADLIK-MO-ResNet50+W3A4Top-177.34—Unverified
3ResNet-18 + 4bit-1dim model compression using DKMTop-170.52—Unverified
4MobileNet-v1 + 4bit-1dim model compression using DKMTop-169.63—Unverified
5ResNet-18 + 2bit-1dim model compression using DKMTop-168.63—Unverified
6MobileNet-v1 + 2bit-1dim model compression using DKMTop-167.62—Unverified
7ResNet-18 + 4bit-4dim model compression using DKMTop-166.1—Unverified
8ResNet-18 + 2bit-2dim model compression using DKMTop-164.7—Unverified
9MobileNet-v1 + 4bit-4dim model compression using DKMTop-161.4—Unverified
10ResNet-18 + 1bit-1dim model compression using DKMTop-159.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MobileBERT + 2bit-1dim model compression using DKMAccuracy82.13—Unverified
2MobileBERT + 1bit-1dim model compression using DKMAccuracy63.17—Unverified